Email this article 
(Department of Industrial Engineering, Faculty of Engineering, Universitas Negeri Yogyakarta, Indonesia)(2) Aktansi Kindiasari
(Manajemen, Fakultas Ekonomi dan Bisnis, Universitas Terbuka, Indonesia)(3) Sulistiyanto Sulistiyanto
(Manajemen Informatika Politeknik Negeri Sriwijaya, Indonesia)*corresponding author
AbstractQuality inspection is a critical process in industrial production to ensure that products meet predefined standards and specifications. Traditionally, quality inspection has relied heavily on manual visual checks, which are time-consuming, subjective, and prone to human error. This study explores the application of computer vision and pattern recognition techniques to develop an automated quality inspection system for industrial products. The proposed system employs high-resolution cameras and image processing algorithms to capture and analyze visual features of products in real-time on the production line. Key techniques utilized include feature extraction, edge detection, and texture analysis to identify defects such as scratches, dents, and dimensional inaccuracies. Pattern recognition algorithms, such as support vector machines (SVM) and convolutional neural networks (CNN), are trained on large datasets of product images to classify items as acceptable or defective with high accuracy. The system was tested on a dataset collected from a manufacturing facility producing metal components. Experimental results demonstrate that the automated system achieved an inspection accuracy of 98%, significantly outperforming manual inspection methods in terms of speed and consistency. Furthermore, the integration of this system into the production line reduced inspection time by approximately 70% and minimized production downtime. This research highlights the potential of intelligent informatics, particularly computer vision and pattern recognition, in enhancing the efficiency, reliability, and scalability of industrial quality control processes. The findings suggest that such automated systems can contribute significantly to the advancement of Industry 4.0 by enabling smart manufacturing practices and reducing dependence on manual labor. Future work will focus on extending the system to handle more complex products and dynamic production environments
|
DOIhttps://doi.org/10.29099/ijair.v9i2.1507 |
Article metrics10.29099/ijair.v9i2.1507 Abstract views : 1 | PDF views : 0 |
Cite |
Full Text Download
|
References
M. F. P. Costa, F. N. S. Medeiros, and others, “Automatic Visual Inspection: A Survey,” Comput. Ind., vol. 49, no. 1, pp. 95–111, 2003.
J. Han, K. Lee, D. Lee, and others, “A Survey On Automated Visual Inspection Technology,” Pattern Recognit., vol. 44, no. 7, pp. 1534–1546, 2011.
S. Li, Y. He, Y. Huang, and others, “Deep Learning In Industrial Inspection: A Survey,” IEEE Trans. Ind. Informatics, vol. 11, no. 3, pp. 656–665, 2015.
W. Chen, C. Liu, and H. Su, “Vision-based automatic surface defect inspection for industrial products,” IEEE Access, vol. 8, pp. 105814–105823, 2020.
R. Szeliski, Computer Vision: Algorithms and Applications. Springer, 2022.
H. Kong, J. Zhang, and others, “Recent advances in visual inspection for industrial applications: a review,” Mach. Vis. Appl., vol. 24, no. 3, pp. 519–535, 2013.
A. Krizhevsky, I. Sutskever, and G. E. Hinton, “ImageNet classification with deep convolutional neural networks,” Adv. Neural Inf. Process. Syst., pp. 1097–1105, 2012.
B. K. P. Horn, Robot Vision. MIT Press, 1986.
N. A. Pusparani, “Qualitative Assessment of e-Government Implementation using PeGI Framework: Case Study Ministry of Marine Affairs and Fisheries the Republic of Indonesia,” 2019 1st International Conference on Cybernetics and Intelligent System, ICORIS 2019. pp. 1–6, 2019, doi: 10.1109/ICORIS.2019.8874881.
T.-Y. Lin, P. Goyal, R. Girshick, and others, “Focal loss for dense object detection,” Proc. IEEE Int. Conf. Comput. Vis., pp. 2980–2988, 2017.
S. Ren, K. He, R. Girshick, and J. Sun, “Faster R-CNN: Towards real-time object detection with region proposal networks,” in Advances in Neural Information Processing Systems (NeurIPS), 2015, pp. 91–99.
M. Tan and Q. Le, “EfficientNet: Rethinking model scaling for convolutional neural networks,” arXiv Prepr. arXiv1905.11946, 2019.
G. Huang, Z. Liu, and others, “Densely connected convolutional networks,” Proc. IEEE Conf. Comput. Vis. Pattern Recognit., pp. 4700–4708, 2017.
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
________________________________________________________
The International Journal of Artificial Intelligence Research
Organized by: Prodi Teknik Informatika Fakultas Teknologi Bisnis dan Sains
Published by: Universitas Dharma Wacana
Jl. Kenanga No. 03 Mulyojati 16C Metro Barat Kota Metro Lampung
Email: jurnal.ijair@gmail.com
This work is licensed under Creative Commons Attribution-ShareAlike 4.0 International License.